#!/opt/homebrew/bin/python3.11
"""
Unified file probe — metadata extraction for all managed file types.
Called by Rust unified_probe() via PythonExecutor.
Output: JSON to stdout.
"""
import sys, json, os

def probe_pdf(path):
    from PyPDF2 import PdfReader
    r = PdfReader(path)
    meta = {"pages": len(r.pages)}
    if r.metadata:
        if r.metadata.get('/Author'): meta["author"] = r.metadata['/Author']
        if r.metadata.get('/Title'):  meta["title"] = r.metadata['/Title']
        if r.metadata.get('/Producer'): meta["producer"] = r.metadata['/Producer']
    return meta

def probe_docx(path):
    from docx import Document
    d = Document(path)
    meta = {"paragraphs": len(d.paragraphs), "sections": len(d.sections)}
    if d.core_properties.author: meta["author"] = d.core_properties.author
    return meta

def probe_xlsx(path):
    import openpyxl
    wb = openpyxl.load_workbook(path, read_only=True)
    meta = {"sheet_names": wb.sheetnames, "sheet_count": len(wb.sheetnames)}
    wb.close()
    return meta

def probe_pptx(path):
    from pptx import Presentation
    prs = Presentation(path)
    meta = {"slide_count": len(prs.slides)}
    texts = []
    for slide in prs.slides:
        for shape in slide.shapes:
            if shape.has_text_frame:
                t = shape.text_frame.text.strip()
                if t: texts.append(t)
    if texts:
        meta["text_preview"] = " | ".join(texts[:5])
    return meta

def probe_archive(path):
    import zipfile, tarfile
    name = os.path.basename(path)
    entries = []
    if name.endswith('.zip'):
        with zipfile.ZipFile(path) as z:
            for e in z.infolist():
                entries.append({"name": e.filename, "size": e.file_size})
    elif name.endswith('.tar') or '.tar.' in name:
        with tarfile.open(path) as t:
            for e in t.getmembers():
                entries.append({"name": e.name, "size": e.size})
    return {"entry_count": len(entries), "entries": entries[:50]}

def probe_iwork(path):
    import zipfile
    try:
        with zipfile.ZipFile(path) as z:
            names = z.namelist()
            has_preview = "preview.pdf" in names or "preview.jpg" in names
            thumb = [n for n in names if "Thumbnail" in n or "preview" in n]
            return {"has_preview": has_preview, "preview_files": thumb}
    except Exception:
        return {"has_preview": False}

def probe(path):
    ext = os.path.splitext(path)[1].lower()
    result = {"streams": []}
    if ext in ('.pdf',):
        result["document"] = probe_pdf(path)
    elif ext in ('.docx', '.doc'):
        result["document"] = probe_docx(path)
    elif ext in ('.xlsx', '.xls'):
        result["spreadsheet"] = probe_xlsx(path)
    elif ext in ('.pptx', '.ppt'):
        result["presentation"] = probe_pptx(path)
    elif ext in ('.pages', '.numbers', '.key'):
        result["apple_iwork"] = probe_iwork(path)
    elif ext in ('.zip', '.tar', '.gz', '.tgz', '.7z', '.rar'):
        result["archive"] = probe_archive(path)
    return json.dumps(result)

if __name__ == '__main__':
    if len(sys.argv) < 2:
        print(json.dumps({"error": "Usage: probe_file.py <path>"}))
        sys.exit(1)
    print(probe(sys.argv[1]))